mlsanityData to 14 Oct 2026

Bringing regularized optimal transport to lightspeed: a splitting method adapted for GPUs

arXiv 2305.18483 ↗First posted 29 May 2023cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

We present an efficient algorithm for regularized optimal transport. In contrast to previous methods, we use the Douglas-Rachford splitting technique to develop an efficient solver that can handle a broad class of regularizers. The algorithm has strong global convergence guarantees, low per-iteration cost, and can exploit GPU parallelization, making it considerably faster than the state-of-the-art for many problems. We illustrate its competitiveness in several applications, including domain adaptation and learning of generative models.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 24 of its 45 references that are in the map. First posted on arXiv 29 May 2023.

Builds on

24 of 45 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  3. 2016Language Modeling with Gated Convolutional Networkscited by 702
  4. 2016Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networkscited by 543
  5. 2015Optimal Transport for Domain Adaptationcited by 463
  6. 2017Learning Generative Models with Sinkhorn Divergencescited by 314
  7. 2017Joint Distribution Optimal Transportation for Domain Adaptationcited by 282
  8. 2017Large-Scale Optimal Transport and Mapping Estimationcited by 123
  9. 2018Improving GANs Using Optimal Transportcited by 123
  10. 2019Differentiable Ranks and Sorting using Optimal Transportcited by 113
  11. 2016Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Unitscited by 86
  12. 2017Smooth and Sparse Optimal Transportcited by 83
12 more
  1. 2016Stabilized Sparse Scaling Algorithms for Entropy Regularized Transport Problemscited by 73
  2. 2019On Efficient Optimal Transport: An Analysis of Greedy and Accelerated Mirror Descent Algorithmscited by 62
  3. 2022Sparsity-Constrained Optimal Transportcited by 32
  4. 2019Quadratically regularized optimal transportcited by 15
  5. 2022Rethinking Initialization of the Sinkhorn Algorithmcited by 14
  6. 2021Faster First-Order Primal-Dual Methods for Linear Programming using Restarts and Sharpnesscited by 13
  7. 2020Optimal Transport losses and Sinkhorn algorithm with general convex regularizationcited by 10
  8. 2021A Fast and Accurate Splitting Method for Optimal Transport: Analysis and Implementationcited by 9
  9. 2022Accelerated Bregman Primal-Dual methods applied to Optimal Transport and Wasserstein Barycenter problemscited by 7
  10. 2019Trajectory of Alternating Direction Method of Multipliers and Adaptive Accelerationcited by 6
  11. 2017Gini-regularized Optimal Transport with an Application to Spatio-Temporal Forecastingcited by 4
  12. 2021Projecting onto rectangular matrices with prescribed row and column sumscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPUcited by 11
  2. 2026cuRegOT: A GPU-Accelerated Solver for Entropic-Regularized Optimal Transportcited by 1
  3. 2026Annealed Sinkhorn with Momentum: Certified Unregularized Optimal Transport in Linear Memorycited by 0